Files
econometrics/Week7/Week7_Stata代码详解.html

47 lines
292 KiB
HTML
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!DOCTYPE html>
<html lang="zh-CN"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><meta name="description" content="week7_analysis.do 的中文逐段代码详解,涵盖全部 165 行:Excel 整理、OLS 回归、残差、分组、绘图与稳健推断。离线 HTML5。"><title>Week 7 · Stata 代码逐段详解</title><style>
:root{--ink:#1d3042;--muted:#536675;--accent:#116b68;--accent-light:#e9f5f1;--border:#dce5e9;--paper:#fff;--bg:#f4f6f8;--code:#162a3a;--serif:Georgia,"Noto Serif SC","Source Han Serif SC","Songti SC",SimSun,serif;--sans:"Segoe UI","Microsoft YaHei","PingFang SC",sans-serif;--mono:Consolas,"Cascadia Code","Microsoft YaHei",monospace}
*{box-sizing:border-box}html{scroll-behavior:smooth;scroll-padding-top:28px}body{margin:0;background:var(--bg);color:var(--ink);font:16px/1.85 var(--sans)}a{color:var(--accent);text-decoration-thickness:1px;text-underline-offset:4px}a:focus-visible,button:focus-visible,summary:focus-visible,.table-wrap:focus-visible{outline:3px solid #dc9a25;outline-offset:4px}.skip-link{position:fixed;top:-70px;left:16px;z-index:9;padding:8px 15px;background:white}.skip-link:focus{top:8px}.reading-progress{position:fixed;top:0;left:0;height:4px;width:0;background:#d6a34c;z-index:10}
header{background:#163549;color:#fff;border-bottom:6px solid #d7aa5c}.hero{max-width:1390px;margin:auto;padding:54px 48px 38px}.eyebrow{font:600 12px/1.5 var(--sans);letter-spacing:2.5px;color:#b9d4d9}.hero h1{font:600 clamp(32px,4vw,50px)/1.32 var(--serif);letter-spacing:.02em;margin:16px 0 14px}.hero h1 span{color:#dcecea}.dek{max-width:850px;color:#d6e3e9;font-size:17px;margin:0 0 23px}.meta{display:flex;gap:9px;flex-wrap:wrap}.meta span{border:1px solid #4b697a;border-radius:4px;padding:4px 11px;font-size:12px;color:#e3edf2}.hero-bottom{display:flex;justify-content:space-between;align-items:center;gap:22px;margin-top:27px;padding-top:22px;border-top:1px solid #446274}.flow{display:flex;flex-wrap:wrap;align-items:center;gap:9px;color:#dce9e8;font-size:13px}.flow b{color:#d7aa5c;font-weight:400}.print-btn{background:transparent;border:1px solid #70919e;color:#fff;border-radius:5px;padding:8px 16px;white-space:nowrap;cursor:pointer;font:inherit;font-size:13px}
.layout{max-width:1390px;margin:auto;display:grid;grid-template-columns:252px minmax(0,1fr);gap:26px;padding:30px 34px 70px}.sidebar{position:sticky;top:24px;align-self:start;max-height:calc(100vh - 48px);overflow:auto;padding:7px 10px 18px 0;scrollbar-width:thin}.sidebar .nav-label{font-size:12px;letter-spacing:2px;color:var(--muted);margin:0 0 12px 10px}.sidebar a{display:block;font-size:13px;line-height:1.5;padding:7px 10px;margin:2px 0;color:#4a5e6d;text-decoration:none;border-left:3px solid transparent;border-radius:0 4px 4px 0}.sidebar a:hover,.sidebar a[aria-current=true]{background:#e3eeed;border-left-color:var(--accent);color:#114d4c}.sidebar .nav-foot{font-size:11px;line-height:1.8;margin:18px 10px;color:#5c6b76}.mobile-nav{display:none}main{min-width:0;background:var(--paper);border:1px solid var(--border);border-radius:9px;padding:35px 42px;box-shadow:0 8px 28px #16354905}.section-heading{display:flex;align-items:flex-start;justify-content:space-between;gap:16px;margin:0 0 20px}.section-heading h2{font:600 24px/1.48 var(--serif);margin:0;color:#16394e;overflow-wrap:anywhere}.line-badge{font:12px/1.5 var(--mono);padding:4px 8px;flex-shrink:0;background:#edf3f6;border:1px solid #d8e2e9;border-radius:4px;color:#435b6b;margin-top:3px}section+section{border-top:1px solid var(--border);padding-top:34px;margin-top:38px}p{margin:14px 0;overflow-wrap:anywhere}strong{font-weight:650;color:#16394e}code{font: .89em/1.6 var(--mono);background:#edf2f5;color:#213e54;border-radius:3px;padding:.1em .3em;overflow-wrap:anywhere}.note{border-left:4px solid #c49b48;padding:14px 19px;margin:22px 0;background:#fcf8ef;border-radius:0 5px 5px 0}.note>strong{font-size:15px;color:#72511c}.note p{font-size:14px;line-height:1.9;margin:5px 0 0}.formula{border-left:4px solid var(--accent);padding:18px 20px;margin:20px 0;background:var(--accent-light);font:500 17px/1.8 var(--serif);color:#154d4b;overflow-wrap:anywhere}
.table-wrap{overflow-x:auto;margin:20px 0;border:1px solid var(--border);border-radius:5px;scrollbar-width:thin}table{border-collapse:collapse;width:100%;font-size:14px;line-height:1.8}th{background:#eff4f6;color:#21485b;text-align:left;font-weight:650;padding:12px 14px;white-space:nowrap}td{padding:12px 14px;vertical-align:top;border-top:1px solid #e4eaee;min-width:100px;overflow-wrap:anywhere}td:first-child{color:#234456;font-weight:500;min-width:155px}tr:nth-child(even) td{background:#fbfcfd}td code{font-size:12.5px;line-height:1.75}th:first-child{width:29%}.code-block{margin:20px 0 24px;border:1px solid #284255;border-radius:6px;overflow:hidden;background:var(--code);color:#e1eaf0}.code-toolbar{display:flex;justify-content:space-between;align-items:center;padding:8px 14px;background:#233d50;border-bottom:1px solid #365265;gap:12px;color:#bed0dc;font:11px/1.5 var(--mono);letter-spacing:.3px}.copy-btn{font:12px/1.4 var(--sans);border:1px solid #688493;border-radius:3px;padding:5px 9px;color:#edf5f8;background:transparent;cursor:pointer;flex-shrink:0}.copy-btn:hover{background:#3b596c}pre{margin:0;padding:15px 0;overflow:visible}pre code{background:none;padding:0;color:inherit;border-radius:0;font:12.8px/1.85 var(--mono);white-space:normal}.code-line{display:grid;grid-template-columns:44px minmax(0,1fr);padding:0 15px 0 0;min-height:1.85em}.ln{user-select:none;text-align:right;padding-right:12px;color:#8aa3b5;white-space:nowrap}.src{white-space:pre-wrap;overflow-wrap:anywhere;tab-size:4}.code-line:hover{background:#233e50}figure{margin:25px 0 20px}figure img{display:block;width:100%;height:auto;border:1px solid #d3dfe6;border-radius:6px}figcaption{font-size:12px;text-align:center;color:var(--muted);padding:9px 10px}footer{max-width:1250px;margin:0 auto 28px;padding:0 30px;font-size:12px;color:#5d6e79;text-align:center}.back-top{position:fixed;right:18px;bottom:18px;background:#174f60;color:white;border:0;border-radius:5px;padding:10px 14px;cursor:pointer;box-shadow:0 3px 12px #16354922;font:13px var(--sans)}.live-status{position:fixed;bottom:24px;left:50%;transform:translateX(-50%);background:#193f50;color:white;padding:8px 15px;border-radius:5px;font-size:13px;z-index:12}.live-status:empty{display:none}
@media(min-width:1500px){.layout{grid-template-columns:270px minmax(0,1fr)}}
@media(max-width:1050px){.layout{grid-template-columns:205px minmax(0,1fr);gap:18px;padding:24px 22px 50px}.hero{padding:40px 32px 30px}main{padding:28px}.sidebar a{font-size:12px}.section-heading h2{font-size:22px}td,th{padding:10px 12px}}
@media(max-width:780px){.sidebar{display:none}.layout{display:block;padding:18px 14px 45px}.mobile-nav{display:block;max-width:100%;background:white;border-bottom:1px solid var(--border);padding:12px 22px}.mobile-nav summary{color:var(--accent);font-weight:600;cursor:pointer}.mobile-nav nav{padding-top:12px;display:grid;grid-template-columns:1fr 1fr;gap:7px}.mobile-nav a{font-size:12px;text-decoration:none;padding:4px}main{padding:26px 24px}.hero{padding:34px 25px 26px}.hero-bottom{align-items:flex-start}.hero h1{font-size:35px}.dek{font-size:15px}.flow{font-size:12px}.section-heading{gap:10px}.section-heading h2{font-size:22px}section+section{padding-top:26px;margin-top:30px}}
@media(max-width:480px){body{font-size:15px}.hero{padding:28px 20px 22px}.hero h1{font-size:30px}.eyebrow{font-size:10px;letter-spacing:1.8px}.hero-bottom{display:block;margin-top:21px;padding-top:17px}.print-btn{margin-top:15px}.meta{gap:6px}.meta span{font-size:11px;padding:3px 7px}.layout{padding:12px 9px 40px}main{padding:22px 16px;border-radius:6px}.section-heading{display:block}.line-badge{display:inline-block;margin-top:9px}.section-heading h2{font-size:21px}.formula{font-size:16px;padding:14px}.note{padding:12px 14px}.note p{font-size:13px}.code-toolbar{padding:8px 9px;font-size:10px;letter-spacing:0}.code-line{grid-template-columns:31px minmax(0,1fr);padding-right:9px}.ln{padding-right:7px}.src{font-size:11.5px}table{font-size:13px}td:first-child{min-width:120px}td{min-width:150px}th{white-space:normal}.mobile-nav nav{grid-template-columns:1fr}.back-top{font-size:12px;padding:9px 11px;right:10px;bottom:10px}}
@media print{html{scroll-behavior:auto}body{background:white;font:10pt/1.6 var(--sans);color:#111}header{background:white;color:#111;border-bottom:2px solid #666}.hero{padding:0 0 18px;max-width:none}.hero h1{font-size:26pt}.hero h1 span,.dek,.eyebrow,.meta span,.flow{color:#222}.meta span{border-color:#aaa}.hero-bottom{border-color:#ccc}.sidebar,.mobile-nav,.print-btn,.copy-btn,.back-top,.reading-progress,.live-status,.skip-link{display:none!important}.layout{display:block;max-width:none;padding:20px 0 0}main{border:0;box-shadow:none;padding:0}.section-heading h2{font-size:16pt}section+section{margin-top:22px;padding-top:20px}.section-heading{break-after:avoid}.line-badge{font-size:9pt}table{font-size:8.5pt}tr{break-inside:avoid}.table-wrap{overflow:visible}td,th{padding:6px 8px;min-width:0!important}th{white-space:normal}.code-block{background:#f5f5f5;border:1px solid #ccc;color:#111;overflow:visible}.code-toolbar{background:#eee;color:#333;border-color:#ccc}.ln{color:#666}pre code,.src{font-size:8pt}.code-line{grid-template-columns:30px minmax(0,1fr)}.formula,.note{break-inside:avoid}.formula{font-size:11pt}figure{break-inside:avoid}footer{font-size:8pt;margin-top:20px}a{color:inherit;text-decoration:none}}
.hero .dek{max-width:1040px}
@media(max-width:480px){.hero h1 span{display:block}}
@media(prefers-reduced-motion:reduce){html{scroll-behavior:auto}}
</style></head><body><a class="skip-link" href="#main">跳转到正文</a><div class="reading-progress" id="reading-progress" aria-hidden="true"></div><header id="top"><div class="hero"><div class="eyebrow">ECONOMETRICS / WEEK 07 / CODE READING</div><h1>读懂每一步,<span>从数据到回归</span></h1><p class="dek">week7_analysis.do 中文逐段详解。对照原文件行号,理解命令如何改变数据、保存结果,以及统计量的实际含义。</p><div class="meta"><span>165 行源代码</span><span>14 个执行步骤</span><span>98 条家庭记录</span><span>Stata 15 语法</span><span>2026-10-26 核对</span></div><div class="hero-bottom"><div class="flow" aria-label="分析流程"><span>Excel 与合计核对</span><b>→</b><span>宽表转长表</span><b>→</b><span>OLS 与残差</span><b>→</b><span>图形与稳健推断</span></div><button id="print-btn" class="print-btn" type="button">打印 / 保存 PDF</button></div></div></header><details class="mobile-nav"><summary>展开章节目录</summary><nav aria-label="移动端章节目录"><a href="#overview">阅读地图:这份 do 文件完成什么</a><a href="#syntax">语法预备:宏、变量、标量与返回值</a><a href="#setup">01 · 初始化环境与记录日志</a><a href="#import">02 · 读取 Excel 的指定数值区域</a><a href="#audit">03 · 逐列检查收入表头并核对合计</a><a href="#export-audit">04 · 临时切换数据并导出审计表</a><a href="#reshape">05 · 从宽表整理成 98 条家庭明细</a><a href="#ols">06 · OLS 回归、拟合值与模型统计量</a><a href="#coefficient-table">07 · 手工整理系数、t 检验与置信区间</a><a href="#residual">08 · 核对 OLS 残差的两个代数性质</a><a href="#group">09 · 按收入水平生成汇总表</a><a href="#plot">10 · 绘制散点与拟合直线,导出四种图形</a><a href="#robust">11 · 计算异方差稳健标准误并导出</a><a href="#hettest">12 · 恢复 OLS 并进行异方差检验</a><a href="#model-export">13 · 将模型汇总指标写成一行 CSV</a><a href="#finish">14 · 完成标记、关闭日志与退出</a><a href="#files">文件索引:每个输出保存了什么</a><a href="#checkpoints">理解与复现时最容易出错的地方</a><a href="#run">如何在给定路径下运行和查阅</a><a href="#sources">核对依据与文档范围</a></nav></details><div class="layout"><aside class="sidebar"><p class="nav-label">阅读目录</p><nav aria-label="章节目录"><a href="#overview">阅读地图:这份 do 文件完成什么</a><a href="#syntax">语法预备:宏、变量、标量与返回值</a><a href="#setup">01 · 初始化环境与记录日志</a><a href="#import">02 · 读取 Excel 的指定数值区域</a><a href="#audit">03 · 逐列检查收入表头并核对合计</a><a href="#export-audit">04 · 临时切换数据并导出审计表</a><a href="#reshape">05 · 从宽表整理成 98 条家庭明细</a><a href="#ols">06 · OLS 回归、拟合值与模型统计量</a><a href="#coefficient-table">07 · 手工整理系数、t 检验与置信区间</a><a href="#residual">08 · 核对 OLS 残差的两个代数性质</a><a href="#group">09 · 按收入水平生成汇总表</a><a href="#plot">10 · 绘制散点与拟合直线,导出四种图形</a><a href="#robust">11 · 计算异方差稳健标准误并导出</a><a href="#hettest">12 · 恢复 OLS 并进行异方差检验</a><a href="#model-export">13 · 将模型汇总指标写成一行 CSV</a><a href="#finish">14 · 完成标记、关闭日志与退出</a><a href="#files">文件索引:每个输出保存了什么</a><a href="#checkpoints">理解与复现时最容易出错的地方</a><a href="#run">如何在给定路径下运行和查阅</a><a href="#sources">核对依据与文档范围</a></nav><p class="nav-foot">代码逐段引用原文件<br>图片、样式与脚本内嵌<br>无网络依赖 · 支持打印</p></aside><main id="main"><section id="overview" aria-labelledby="heading-overview"><div class="section-heading"><h2 id="heading-overview">阅读地图:这份 do 文件完成什么</h2></div><p>这是一份从 Excel 家庭消费明细出发的完整 Stata 分析脚本:核对源表 → 转成长表 → 估计消费与收入的 OLS 关系 → 保存拟合值与残差 → 分组汇总与绘图 → 计算稳健标准误及异方差检验 → 导出结果。回归单位是 98 条家庭记录,收入有 10 个水平。</p><p>本文编写和独立核对日期为 <strong>2026 年 10 月 26 日</strong>;所引 Stata 数值来自工作目录内 <strong>2026 年 10 月 23 日</strong>的运行日志及 CSV。此次没有重跑或改动原 do 文件,也没有改写既有分析产物。我们从原 Excel 独立复算了主要统计量,确认它们与现有输出一致。下文代码块直接截取原文件,L 表示原文件物理行号。</p><div class="formula">拟合消费 = 22.930934 + 0.728798742 × 月收入;N = 98;R² = 0.930666</div><div class="table-wrap" tabindex="0" role="region" aria-label="阅读地图:这份 do 文件完成什么:解释表"><table><thead><tr><th scope="col">输入 / 输出角色</th><th scope="col">内容</th></tr></thead><tbody><tr><td>原始输入</td><td><code>Eg2_1_1/Eg2_1_1.xlsx</code>,工作表 <code>Sheet1</code>,区域 <code>C3:L17</code>。</td></tr><tr><td>被解释变量 Y</td><td><code>consume</code>:每月消费支出,单位元。</td></tr><tr><td>解释变量 X</td><td><code>income</code>:每月可支配收入,单位元。</td></tr><tr><td>主要文件</td><td>DTA 保存数据,CSV 便于通用读取,STER 保存估计结果,GPH/PNG/SVG/PDF 保存图形,LOG 保存运行过程。</td></tr><tr><td>软件与版本</td><td>用户提供的可执行文件为 <code>D:/Stata15/StataSE-64.exe</code>;既有批处理日志显示 Stata/SE 15.1,脚本用 <code>version 15.0</code> 指定兼容行为。</td></tr></tbody></table></div><aside class="note"><strong>先抓住三个区别</strong><p>Excel 行号不等于导入后的 Stata 观测号;<code>preserve/restore</code> 管数据,而 <code>estimates store/restore</code> 管估计结果;<code>vce(robust)</code> 改变标准误和推断,当前模型的 OLS 系数与拟合值保持相同。</p></aside></section><section id="syntax" aria-labelledby="heading-syntax"><div class="section-heading"><h2 id="heading-syntax">语法预备:宏、变量、标量与返回值</h2></div><div class="table-wrap" tabindex="0" role="region" aria-label="语法预备:宏、变量、标量与返回值:解释表"><table><thead><tr><th scope="col">写法</th><th scope="col">在本脚本中的含义</th></tr></thead><tbody><tr><td><code>local income = 800</code> / <code>`income&#x27;</code></td><td>local 定义局部宏;左反引号与右单引号取出宏内容。例如循环首轮 income 宏展开为 800。它不是数据列。</td></tr><tr><td><code>`col&#x27;[1]</code></td><td>若 col 宏是 C,展开为 C[1]:C 变量的第 1 条观测。方括号是观测下标。</td></tr><tr><td><code>consume`income&#x27;</code></td><td>拼接变量名:首轮得到 consume800,下一轮得到 consume1100。</td></tr><tr><td><code>generate income = ...</code> / <code>income</code></td><td>generate 创建数据列;reshape 后的 income 是每条记录都有的数值变量。宏与同名变量用引用语法区分。</td></tr><tr><td><code>scalar slope_ols = ...</code></td><td>保存一个数值;<code>scalar(slope_ols)</code> 明确取标量,可避免与变量名混淆。</td></tr><tr><td><code>r(N)</code>、<code>r(sum)</code>、<code>r(varlist)</code></td><td>一般统计或数据命令返回的结果。summarize 返回 N 和 sum;ds 返回变量名列表。后续 r-class 命令可能覆盖 r(),所以及时保存。</td></tr><tr><td><code>e(N)</code>、<code>e(r2)</code>、<code>e(df_r)</code></td><td>当前估计命令返回的结果;下一次 regress 会改写当前 e()。</td></tr><tr><td><code>_b[income]</code>、<code>_se[income]</code>、<code>_cons</code></td><td>当前模型中 income 的系数、标准误,以及截距项的名字。</td></tr><tr><td><code>_n</code> 与 <code>_N</code></td><td>分别是当前观测的序号、当前数据集观测总数;删行和排序后含义随当前数据变化。</td></tr><tr><td><code>=</code>、<code>==</code>、<code>!</code>、<code>^</code></td><td>分别常用于赋值/表达式计算、相等比较、逻辑非、乘方。<code>assert _N == 98</code> 是检验,不是赋值。</td></tr><tr><td>逗号后的内容</td><td>一般是命令选项,例如 <code>regress consume income, vce(robust)</code>。</td></tr><tr><td><code>quietly</code> / <code>capture</code></td><td>quietly 隐藏普通输出但仍计算并返回结果;capture 捕获错误,允许程序继续。本文件只在关闭旧日志时使用 capture。</td></tr><tr><td><code>replace</code></td><td>在 save/export/log 等命令中表示覆盖同名文件;它不同于单独的 replace 命令修改变量值。</td></tr><tr><td><code>tempname</code></td><td>为文件句柄、标量或矩阵等对象取得唯一临时名称。本文件把名称放进局部宏,交给 postfile 使用;它不让指定的 DTA 文件变成临时文件。</td></tr></tbody></table></div><p>局部宏应连同定义和使用它的代码一起执行;在编辑器中分开执行几段,可能丢失上一段的局部宏上下文。代码中的单引号也不要替换成中文弯引号。语法依据:本机官方帮助 [S1]、[S2]、[S5]。</p></section><section id="setup" aria-labelledby="heading-setup"><div class="section-heading"><h2 id="heading-setup">01 · 初始化环境与记录日志</h2><span class="line-badge">L1–8</span></div><div class="code-block" data-source="dmVyc2lvbiAxNS4wCmNsZWFyIGFsbApzZXQgbW9yZSBvZmYKc2V0IHR5cGUgZG91YmxlCnNldCBsaW5lc2l6ZSAxNjAKY2FwdHVyZSBsb2cgY2xvc2UgX2FsbApjZCAiQzovVXNlcnMvY2F0dG9tL0RvY3VtZW50cy9lY29ub21ldHJpY3MvV2VlazciCmxvZyB1c2luZyAid2Vlazdfc3RhdGEubG9nIiwgdGV4dCByZXBsYWNl"><div class="code-toolbar"><span>STATA · 原文件 L1–8</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">1</span><span class="src">version 15.0</span></span><span class="code-line"><span class="ln" aria-hidden="true">2</span><span class="src">clear all</span></span><span class="code-line"><span class="ln" aria-hidden="true">3</span><span class="src">set more off</span></span><span class="code-line"><span class="ln" aria-hidden="true">4</span><span class="src">set type double</span></span><span class="code-line"><span class="ln" aria-hidden="true">5</span><span class="src">set linesize 160</span></span><span class="code-line"><span class="ln" aria-hidden="true">6</span><span class="src">capture log close _all</span></span><span class="code-line"><span class="ln" aria-hidden="true">7</span><span class="src">cd &quot;C:/Users/cattom/Documents/econometrics/Week7&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">8</span><span class="src">log using &quot;week7_stata.log&quot;, text replace</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="01 · 初始化环境与记录日志:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L1 · <code>version 15.0</code></td><td>按 Stata 15.0 的版本兼容规则解释命令;不是安装或切换可执行软件版本。</td></tr><tr><td>L2 · <code>clear all</code></td><td>清理当前内存数据和估计等工作状态,为整段分析建立干净起点。</td></tr><tr><td>L3 · <code>set more off</code></td><td>关闭长输出的分页暂停,便于批量运行。</td></tr><tr><td>L4 · <code>set type double</code></td><td>未显式指定类型的新数值变量默认使用 double;不等于把所有已有或导入变量自动转成 double。后面的 int 仍按显式类型创建。</td></tr><tr><td>L5 · <code>set linesize 160</code></td><td>设置文本输出行宽为 160,减少长表格折行;不改变数据或网页宽度。</td></tr><tr><td>L6 · <code>capture log close _all</code></td><td>关闭已打开的所有日志;没有日志时产生的错误由 capture 捕获,不中断程序。</td></tr><tr><td>L7 · <code>cd ...</code></td><td>切换工作目录。后续相对路径都以这里为起点;换电脑运行时须修改这个硬编码路径。</td></tr><tr><td>L8 · <code>log using ...</code></td><td>把后续命令和结果记录到 week7_stata.log;text 指定纯文本,replace 覆盖同名旧日志。</td></tr></tbody></table></div><p>double 是存储类型,format 是显示格式,两者不可互换。增加显示位数不能恢复已经丢失的数值精度。官方帮助:[S1]、[S3]。</p></section><section id="import" aria-labelledby="heading-import"><div class="section-heading"><h2 id="heading-import">02 · 读取 Excel 的指定数值区域</h2><span class="line-badge">L10–12</span></div><div class="code-block" data-source="ZGlzcGxheSAiV2VlayA3OiBob3VzZWhvbGQgY29uc3VtcHRpb24gYW5kIGRpc3Bvc2FibGUgaW5jb21lIgpkaXNwbGF5ICJJbnB1dDogbnVtZXJpYyBjZWxscyBDMzpMMTc7IHJvdyAxNyBjb250YWlucyByZXBvcnRlZCB0b3RhbHMuIgppbXBvcnQgZXhjZWwgdXNpbmcgIkVnMl8xXzEvRWcyXzFfMS54bHN4Iiwgc2hlZXQoIlNoZWV0MSIpIGNlbGxyYW5nZShDMzpMMTcpIGNsZWFy"><div class="code-toolbar"><span>STATA · 原文件 L10–12</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">10</span><span class="src">display &quot;Week 7: household consumption and disposable income&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">11</span><span class="src">display &quot;Input: numeric cells C3:L17; row 17 contains reported totals.&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">12</span><span class="src">import excel using &quot;Eg2_1_1/Eg2_1_1.xlsx&quot;, sheet(&quot;Sheet1&quot;) cellrange(C3:L17) clear</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="02 · 读取 Excel 的指定数值区域:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L10–11 · <code>display</code></td><td>只打印分析标题和输入范围说明,不生成变量,也不验证数据。</td></tr><tr><td>L12 · <code>import excel using ...</code></td><td>从相对路径的工作簿导入 Sheet1 的 C3:L17。clear 允许替换内存数据。</td></tr><tr><td>L12 · 没有 <code>firstrow</code></td><td>收入数值表头仍作为第 1 条观测读入;这里变量名为 Excel 列字母 C、D、…、L,后续循环会使用这些名字。</td></tr></tbody></table></div><div class="table-wrap" tabindex="0" role="region" aria-label="02 · 读取 Excel 的指定数值区域:解释表"><table><thead><tr><th scope="col">Excel 位置</th><th scope="col">刚导入时的 Stata 观测号</th><th scope="col">含义</th></tr></thead><tbody><tr><td>C3:L3</td><td>第 1 条</td><td>收入水平:800、1100、1400、…、3500。</td></tr><tr><td>C4:L16</td><td>第 2–14 条</td><td>消费明细,13 行 × 10 列;部分为空白。</td></tr><tr><td>C17:L17</td><td>第 15 条</td><td>原表报告的合计,只用于核对。</td></tr></tbody></table></div><aside class="note"><strong>不要把数字表头当成变量名</strong><p>若在这里直接加 firstrow,后续按 C–L 命名和第 1、15 条观测取值的逻辑就需要一起调整。原代码的行号依赖当前导入范围。</p></aside><p>导入语法与 firstrow 行为依据本机官方帮助 [S4];具体单元格结构已从当前工作簿核对。</p></section><section id="audit" aria-labelledby="heading-audit"><div class="section-heading"><h2 id="heading-audit">03 · 逐列检查收入表头并核对合计</h2><span class="line-badge">L14–27</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L14–27</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">14</span><span class="src">tempname audit</span></span><span class="code-line"><span class="ln" aria-hidden="true">15</span><span class="src">postfile `audit&#x27; double income int n double detail_total reported_total difference using &quot;source_totals_audit.dta&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">16</span><span class="src">local income = 800</span></span><span class="code-line"><span class="ln" aria-hidden="true">17</span><span class="src">foreach col in C D E F G H I J K L {</span></span><span class="code-line"><span class="ln" aria-hidden="true">18</span><span class="src"> assert `col&#x27;[1] == `income&#x27;</span></span><span class="code-line"><span class="ln" aria-hidden="true">19</span><span class="src"> quietly summarize `col&#x27; in 2/14</span></span><span class="code-line"><span class="ln" aria-hidden="true">20</span><span class="src"> local count = r(N)</span></span><span class="code-line"><span class="ln" aria-hidden="true">21</span><span class="src"> local total = r(sum)</span></span><span class="code-line"><span class="ln" aria-hidden="true">22</span><span class="src"> local reported = `col&#x27;[15]</span></span><span class="code-line"><span class="ln" aria-hidden="true">23</span><span class="src"> post `audit&#x27; (`income&#x27;) (`count&#x27;) (`total&#x27;) (`reported&#x27;) (`total&#x27; - `reported&#x27;)</span></span><span class="code-line"><span class="ln" aria-hidden="true">24</span><span class="src"> rename `col&#x27; consume`income&#x27;</span></span><span class="code-line"><span class="ln" aria-hidden="true">25</span><span class="src"> local income = `income&#x27; + 300</span></span><span class="code-line"><span class="ln" aria-hidden="true">26</span><span class="src">}</span></span><span class="code-line"><span class="ln" aria-hidden="true">27</span><span class="src">postclose `audit&#x27;</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="03 · 逐列检查收入表头并核对合计:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L14 · <code>tempname audit</code></td><td>创建唯一的临时句柄名,放在局部宏 audit 中,避免与已有对象重名。</td></tr><tr><td>L15 · <code>postfile ... using ...</code></td><td>声明新的审计结果表:income 收入、n 非缺失条数、detail_total 明细和、reported_total 原表合计、difference 差额;n 用 int,其余字段按声明使用 double。不会替换当前 Excel 数据。</td></tr><tr><td>L16–17 · <code>local</code> + <code>foreach</code></td><td>从收入 800 开始,按 C 到 L 的顺序循环 10 次。每轮 col 宏代表一个列名。</td></tr><tr><td>L18 · <code>assert</code></td><td>确认当前列第 1 条观测等于预期收入。若表头或列顺序不符,断言失败,脚本停止。</td></tr><tr><td>L19 · <code>quietly summarize ... in 2/14</code></td><td>只汇总明细所在的第 2–14 条观测;缺失值不参加计数和求和;quietly 仅隐藏输出。</td></tr><tr><td>L20–22 · 三个 <code>local</code></td><td>保存 r(N)、r(sum) 和第 15 条观测中的原表合计,以免之后命令覆盖 r()。</td></tr><tr><td>L23 · <code>post</code></td><td>按声明顺序写入一条审计记录。差额 = 明细之和 − 原表合计;每个待写表达式分别放在括号中。</td></tr><tr><td>L24 · <code>rename</code></td><td>例如把 C 改名为 consume800,把 D 改名为 consume1100,为 reshape 的共同前缀 consume 做准备。</td></tr><tr><td>L25–26 · 收入递增、结束循环</td><td>收入宏每轮增加 300,与下一个列的收入表头对应。最后一轮处理 consume3500。</td></tr><tr><td>L27 · <code>postclose</code></td><td>完成写入并关闭句柄,使 source_totals_audit.dta 可被后续 use 读入。</td></tr></tbody></table></div><p>首轮循环可读成:检查 C[1] = 800 → 统计 C[2] 到 C[14] → 读取 C[15] → 写入审计表 → 把 C 改名为 consume800 → 把收入宏改成 1100。postfile/post/postclose 的行为依据 [S2],summarize 返回值依据 [S5]。</p><div class="table-wrap" tabindex="0" role="region" aria-label="03 · 逐列检查收入表头并核对合计:解释表"><table><thead><tr><th scope="col">收入</th><th scope="col">有效明细数</th><th scope="col">明细之和</th><th scope="col">原表合计</th><th scope="col">差额</th></tr></thead><tbody><tr><td>800</td><td>4</td><td>2420</td><td>2420</td><td>+0</td></tr><tr><td>1100</td><td>6</td><td>4950</td><td>4950</td><td>+0</td></tr><tr><td>1400</td><td>11</td><td>11495</td><td>11495</td><td>+0</td></tr><tr><td>1700</td><td>13</td><td>16445</td><td>16445</td><td>+0</td></tr><tr><td>2000</td><td>13</td><td>19305</td><td>19305</td><td>+0</td></tr><tr><td>2300</td><td>13</td><td>21868</td><td>23870</td><td>-2002</td></tr><tr><td>2600</td><td>13</td><td>25025</td><td>25025</td><td>+0</td></tr><tr><td>2900</td><td>10</td><td>21362</td><td>21450</td><td>-88</td></tr><tr><td>3200</td><td>9</td><td>21153</td><td>21285</td><td>-132</td></tr><tr><td>3500</td><td>6</td><td>15499</td><td>15510</td><td>-11</td></tr></tbody></table></div><aside class="note"><strong>审计记录差异,但不会自动修正</strong><p>有 4 组合计不一致:2300、2900、3200、3500 元组的差额分别为 −2002、−88、−132、−11 元。代码没有 assert difference == 0,因此发现差异后继续分析明细;它既不按合计反推缺失值,也不把合计行加入回归。</p></aside></section><section id="export-audit" aria-labelledby="heading-export-audit"><div class="section-heading"><h2 id="heading-export-audit">04 · 临时切换数据并导出审计表</h2><span class="line-badge">L28–34</span></div><div class="code-block" data-source="cHJlc2VydmUKICAgIHVzZSAic291cmNlX3RvdGFsc19hdWRpdC5kdGEiLCBjbGVhcgogICAgbGlzdCwgbm9vYnMgc2VwYXJhdG9yKDApCiAgICBxdWlldGx5IGRzLCBoYXModHlwZSBudW1lcmljKQogICAgZm9ybWF0IGByKHZhcmxpc3QpJyAlMjEuMTVnCiAgICBleHBvcnQgZGVsaW1pdGVkIHVzaW5nICJzb3VyY2VfdG90YWxzX2F1ZGl0LmNzdiIsIGRhdGFmbXQgcmVwbGFjZQpyZXN0b3Jl"><div class="code-toolbar"><span>STATA · 原文件 L28–34</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">28</span><span class="src">preserve</span></span><span class="code-line"><span class="ln" aria-hidden="true">29</span><span class="src"> use &quot;source_totals_audit.dta&quot;, clear</span></span><span class="code-line"><span class="ln" aria-hidden="true">30</span><span class="src"> list, noobs separator(0)</span></span><span class="code-line"><span class="ln" aria-hidden="true">31</span><span class="src"> quietly ds, has(type numeric)</span></span><span class="code-line"><span class="ln" aria-hidden="true">32</span><span class="src"> format `r(varlist)&#x27; %21.15g</span></span><span class="code-line"><span class="ln" aria-hidden="true">33</span><span class="src"> export delimited using &quot;source_totals_audit.csv&quot;, datafmt replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">34</span><span class="src">restore</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="04 · 临时切换数据并导出审计表:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L28 · <code>preserve</code></td><td>暂存当前已改名的 Excel 宽表。</td></tr><tr><td>L29 · <code>use ... , clear</code></td><td>把内存数据切换成刚生成的审计 DTA 文件。</td></tr><tr><td>L30 · <code>list, noobs separator(0)</code></td><td>列出审计表;noobs 不显示观测序号,separator(0) 不插入分隔线。</td></tr><tr><td>L31 · <code>quietly ds, has(type numeric)</code></td><td>找出数值型变量,将变量名列表放在 r(varlist) 中。</td></tr><tr><td>L32 · <code>format `r(varlist)&#x27; %21.15g</code></td><td>给这些变量设置宽度 21、精度参数 15 的通用数值显示格式 g;必要时使用科学计数法,不是固定 15 位小数。</td></tr><tr><td>L33 · <code>export delimited ... , datafmt replace</code></td><td>导出 CSV。datafmt 使用刚设定的显示格式;replace 覆盖同名文件。</td></tr><tr><td>L34 · <code>restore</code></td><td>恢复 L28 时保存的宽表;之后继续处理家庭明细。</td></tr></tbody></table></div><p>“preserve → 切换/汇总数据 → 导出 → restore”在文件中多次出现,是 Stata 15 单数据集工作流的核心。preserve/restore 不代替 estimates store/restore;数据恢复不应被当作模型恢复。DTA 保存存储值与元数据,CSV 保存文本,显示精度可能影响 CSV 的文本表示。[S3]、[S6]</p></section><section id="reshape" aria-labelledby="heading-reshape"><div class="section-heading"><h2 id="heading-reshape">05 · 从宽表整理成 98 条家庭明细</h2><span class="line-badge">L36–53</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L36–53</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">36</span><span class="src">keep in 2/14</span></span><span class="code-line"><span class="ln" aria-hidden="true">37</span><span class="src">generate int excel_row = _n + 3</span></span><span class="code-line"><span class="ln" aria-hidden="true">38</span><span class="src">reshape long consume, i(excel_row) j(income)</span></span><span class="code-line"><span class="ln" aria-hidden="true">39</span><span class="src">drop if missing(consume)</span></span><span class="code-line"><span class="ln" aria-hidden="true">40</span><span class="src">sort income excel_row</span></span><span class="code-line"><span class="ln" aria-hidden="true">41</span><span class="src">generate int household_id = _n</span></span><span class="code-line"><span class="ln" aria-hidden="true">42</span><span class="src">order household_id excel_row income consume</span></span><span class="code-line"><span class="ln" aria-hidden="true">43</span><span class="src">assert _N == 98</span></span><span class="code-line"><span class="ln" aria-hidden="true">44</span><span class="src">assert !missing(income, consume)</span></span><span class="code-line"><span class="ln" aria-hidden="true">45</span><span class="src">label variable income &quot;每月可支配收入(元)&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">46</span><span class="src">label variable consume &quot;每月消费支出(元)&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">47</span><span class="src">label variable excel_row &quot;Source worksheet row&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">48</span><span class="src">label variable household_id &quot;Record identifier&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">49</span><span class="src">save &quot;households_clean.dta&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">50</span><span class="src">quietly ds, has(type numeric)</span></span><span class="code-line"><span class="ln" aria-hidden="true">51</span><span class="src"> format `r(varlist)&#x27; %21.15g</span></span><span class="code-line"><span class="ln" aria-hidden="true">52</span><span class="src">export delimited using &quot;households_clean.csv&quot;, datafmt replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">53</span><span class="src">summarize income consume</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="05 · 从宽表整理成 98 条家庭明细:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L36 · <code>keep in 2/14</code></td><td>仅保留当前宽表第 2–14 条观测:去掉收入表头和合计行,余下 13 行。</td></tr><tr><td>L37 · <code>generate int excel_row = _n + 3</code></td><td>keep 后 _n 从 1 重新编号;加 3 后得到原 Excel 行号 4–16。这是追溯来源的行标记。</td></tr><tr><td>L38 · <code>reshape long consume, i(excel_row) j(income)</code></td><td>将 consume800 至 consume3500 堆叠成长变量 consume;i() 标记原宽表行,j() 把后缀 800…3500 提取成数值变量 income。</td></tr><tr><td>L39 · <code>drop if missing(consume)</code></td><td>删除没有消费明细的组合。先形成 13 × 10 = 130 条,再删除 32 条缺失记录,剩 98 条;不会删除数值为 0 的消费。</td></tr><tr><td>L40–41 · <code>sort</code>、<code>generate ... household_id</code></td><td>按收入、原表行号排序,再以 _n 建立 1–98 的记录编号。编号是人为生成的,不是原始调查家庭 ID。</td></tr><tr><td>L42 · <code>order ...</code></td><td>把四个变量按指定顺序排列;不改变数值。</td></tr><tr><td>L43 · <code>assert _N == 98</code></td><td>检查总记录数恰好为 98;若数据版本或整理逻辑变化,会停止提醒。</td></tr><tr><td>L44 · <code>assert !missing(income, consume)</code></td><td>检查每条观测的收入与消费均非缺失;missing() 在任一参数缺失时为真,! 将其取反。</td></tr><tr><td>L45–48 · <code>label variable</code></td><td>设置四个变量的说明标签;变量名仍是 income、consume 等。DTA 保存标签,普通 CSV 不保留完整 Stata 元数据。</td></tr><tr><td>L49 · <code>save ... , replace</code></td><td>保存清洗后的 DTA;此时尚未生成拟合值、残差。</td></tr><tr><td>L50–52 · <code>ds</code>、<code>format</code>、<code>export delimited</code></td><td>复用数值变量筛选和高精度 CSV 导出步骤。缩进只是排版,这几行不属于新的代码块。</td></tr><tr><td>L53 · <code>summarize income consume</code></td><td>打印收入与消费的个数、均值、标准差、最小值和最大值,进行基本描述统计。</td></tr></tbody></table></div><div class="table-wrap" tabindex="0" role="region" aria-label="05 · 从宽表整理成 98 条家庭明细:解释表"><table><thead><tr><th scope="col">原 Excel 单元格</th><th scope="col">reshape 前</th><th scope="col">reshape 后的一条记录</th></tr></thead><tbody><tr><td>C4 = 561</td><td>excel_row=4,consume800=561</td><td>excel_row=4,income=800,consume=561</td></tr><tr><td>D4 = 638</td><td>excel_row=4,consume1100=638</td><td>excel_row=4,income=1100,consume=638</td></tr></tbody></table></div><aside class="note"><strong>同一 Excel 行不代表同一个家庭</strong><p>第 4 行的不同收入列属于不同家庭消费记录。因此长表中 excel_row 会重复,(excel_row, income) 才标记具体来源单元格。本脚本没有把这批数据设为面板数据,也没有做去重。相同金额可以来自不同家庭。</p></aside><p>当前数据平均收入为 2202.0408 元,平均消费为 1627.7755 元。所有 98 条明细逐一与原 Excel 的收入、消费及行号一致。reshape 的 i()/j() 语义依据 [S4]。</p></section><section id="ols" aria-labelledby="heading-ols"><div class="section-heading"><h2 id="heading-ols">06 · OLS 回归、拟合值与模型统计量</h2><span class="line-badge">L55–69</span></div><div class="code-block" data-source="cmVncmVzcyBjb25zdW1lIGluY29tZQplc3RpbWF0ZXMgc3RvcmUgT0xTCmVzdGltYXRlcyBzYXZlICJjb25zdW1wdGlvbl9vbHMuc3RlciIsIHJlcGxhY2UKcHJlZGljdCBkb3VibGUgZml0dGVkLCB4YgpwcmVkaWN0IGRvdWJsZSByZXNpZHVhbCwgcmVzaWR1YWxzCmdlbmVyYXRlIGRvdWJsZSByZXNpZHVhbF9zcSA9IHJlc2lkdWFsXjIKc2NhbGFyIHNsb3BlX29scyA9IF9iW2luY29tZV0Kc2NhbGFyIGludGVyY2VwdF9vbHMgPSBfYltfY29uc10Kc2NhbGFyIHJzcXVhcmVkX29scyA9IGUocjIpCnNjYWxhciBybXNlX29scyA9IGUocm1zZSkKc2NhbGFyIHJzc19vbHMgPSBlKHJzcykKc2NhbGFyIE5fb2xzID0gZShOKQpzY2FsYXIgRl9vbHMgPSBlKEYpCnNjYWxhciBkZl9vbHMgPSBlKGRmX3IpCnNjYWxhciBwRl9vbHMgPSBGdGFpbChlKGRmX20pLCBlKGRmX3IpLCBlKEYpKQ=="><div class="code-toolbar"><span>STATA · 原文件 L55–69</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">55</span><span class="src">regress consume income</span></span><span class="code-line"><span class="ln" aria-hidden="true">56</span><span class="src">estimates store OLS</span></span><span class="code-line"><span class="ln" aria-hidden="true">57</span><span class="src">estimates save &quot;consumption_ols.ster&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">58</span><span class="src">predict double fitted, xb</span></span><span class="code-line"><span class="ln" aria-hidden="true">59</span><span class="src">predict double residual, residuals</span></span><span class="code-line"><span class="ln" aria-hidden="true">60</span><span class="src">generate double residual_sq = residual^2</span></span><span class="code-line"><span class="ln" aria-hidden="true">61</span><span class="src">scalar slope_ols = _b[income]</span></span><span class="code-line"><span class="ln" aria-hidden="true">62</span><span class="src">scalar intercept_ols = _b[_cons]</span></span><span class="code-line"><span class="ln" aria-hidden="true">63</span><span class="src">scalar rsquared_ols = e(r2)</span></span><span class="code-line"><span class="ln" aria-hidden="true">64</span><span class="src">scalar rmse_ols = e(rmse)</span></span><span class="code-line"><span class="ln" aria-hidden="true">65</span><span class="src">scalar rss_ols = e(rss)</span></span><span class="code-line"><span class="ln" aria-hidden="true">66</span><span class="src">scalar N_ols = e(N)</span></span><span class="code-line"><span class="ln" aria-hidden="true">67</span><span class="src">scalar F_ols = e(F)</span></span><span class="code-line"><span class="ln" aria-hidden="true">68</span><span class="src">scalar df_ols = e(df_r)</span></span><span class="code-line"><span class="ln" aria-hidden="true">69</span><span class="src">scalar pF_ols = Ftail(e(df_m), e(df_r), e(F))</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="06 · OLS 回归、拟合值与模型统计量:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L55 · <code>regress consume income</code></td><td>第一个变量 consume 是因变量,income 是解释变量;默认含截距,按 98 条明细等权估计 OLS。</td></tr><tr><td>L56 · <code>estimates store OLS</code></td><td>把当前估计结果以 OLS 这个名字保存在内存中,供后面恢复。</td></tr><tr><td>L57 · <code>estimates save ...</code></td><td>把当前估计结果写入磁盘 STER 文件。它与保存家庭数据的 save 不同,之后可用 estimates use 载入。</td></tr><tr><td>L58 · <code>predict double fitted, xb</code></td><td>生成线性预测 fitted = 截距 + 收入系数 × income;xb 表示设计矩阵与系数向量的乘积。</td></tr><tr><td>L59 · <code>predict double residual, residuals</code></td><td>生成残差 residual = 实际消费 − fitted。</td></tr><tr><td>L60 · <code>generate double residual_sq = residual^2</code></td><td>生成残差平方,便于保留逐户误差信息。后续 estat hettest 自行从估计结果计算所需量,不直接读取这个命名变量。</td></tr><tr><td>L61–62 · <code>_b[income]</code>、<code>_b[_cons]</code></td><td>分别保存斜率和截距为标量。</td></tr><tr><td>L63–66 · <code>e(r2)</code>、<code>e(rmse)</code>、<code>e(rss)</code>、<code>e(N)</code></td><td>分别保存 R²、残差标准差估计(Root MSE)、残差平方和、估计样本量。</td></tr><tr><td>L67–68 · <code>e(F)</code>、<code>e(df_r)</code></td><td>保存常规模型 F 统计量与残差自由度,本例自由度为 98−2=96。</td></tr><tr><td>L69 · <code>Ftail(...)</code></td><td>用 F 分布右尾概率计算整体显著性 p 值;参数依次为模型自由度、残差自由度、F 值,本例为 F(1,96)。</td></tr></tbody></table></div><div class="formula">Yᵢ = β₀ + β₁Xᵢ + uᵢ;OLS 最小化 Σ(Yᵢ − β̂₀ − β̂₁Xᵢ)²。</div><div class="formula">Ŷᵢ = β̂₀ + β̂₁Xᵢ;êᵢ = Yᵢ − Ŷᵢ;RSS = Σêᵢ²;Root MSE = √[RSS/(N−2)]。</div><div class="table-wrap" tabindex="0" role="region" aria-label="06 · OLS 回归、拟合值与模型统计量:解释表"><table><thead><tr><th scope="col">统计量</th><th scope="col">现有输出</th><th scope="col">如何理解</th></tr></thead><tbody><tr><td>截距 / 斜率</td><td>22.930934 / 0.728798742</td><td>收入高 100 元,拟合消费高约 72.88 元。0 收入在样本范围外,截距不宜作实质外推。</td></tr><tr><td>N / 残差自由度</td><td>98 / 96</td><td>估计了截距与一个斜率,共 2 个参数。</td></tr><tr><td>R²</td><td>0.930665683</td><td>收入的线性拟合解释约 93.07% 的消费总离差平方和,不是预测正确率。</td></tr><tr><td>Root MSE</td><td>146.627814 元</td><td>按残差自由度调整后的残差尺度;不是除以 N 的样本内预测 RMSE。</td></tr><tr><td>RSS</td><td>2063972.732587 元²</td><td>残差平方和。</td></tr><tr><td>F / p_F</td><td>1288.595737 / 1.9519e-57</td><td>本例整体检验是 H₀: β₁=0,不把截距同时设为 0。</td></tr></tbody></table></div><p>拟合值不是实际消费,也不是已知的真实总体条件均值;残差 êᵢ 是估计后可计算的量,真实扰动 uᵢ 通常不可观测。这里的收入系数描述样本中的线性关系;单变量回归本身不建立因果识别。保存标量还可防止后续稳健回归替换 e() 后丢失常规模型统计量。[S7]、[S8]</p></section><section id="coefficient-table" aria-labelledby="heading-coefficient-table"><div class="section-heading"><h2 id="heading-coefficient-table">07 · 手工整理系数、t 检验与置信区间</h2><span class="line-badge">L71–84</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L71–84</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">71</span><span class="src">tempname coef</span></span><span class="code-line"><span class="ln" aria-hidden="true">72</span><span class="src">postfile `coef&#x27; str12 term double estimate double se double t double p double ci_low double ci_high using &quot;regression_coefficients.dta&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">73</span><span class="src">foreach term in income _cons {</span></span><span class="code-line"><span class="ln" aria-hidden="true">74</span><span class="src"> scalar tval = _b[`term&#x27;] / _se[`term&#x27;]</span></span><span class="code-line"><span class="ln" aria-hidden="true">75</span><span class="src"> scalar crit = invttail(e(df_r), .025)</span></span><span class="code-line"><span class="ln" aria-hidden="true">76</span><span class="src"> post `coef&#x27; (&quot;`term&#x27;&quot;) (_b[`term&#x27;]) (_se[`term&#x27;]) (tval) (2*ttail(e(df_r), abs(tval))) (_b[`term&#x27;]-crit*_se[`term&#x27;]) (_b[`term&#x27;]+crit*_se[`term&#x27;])</span></span><span class="code-line"><span class="ln" aria-hidden="true">77</span><span class="src">}</span></span><span class="code-line"><span class="ln" aria-hidden="true">78</span><span class="src">postclose `coef&#x27;</span></span><span class="code-line"><span class="ln" aria-hidden="true">79</span><span class="src">preserve</span></span><span class="code-line"><span class="ln" aria-hidden="true">80</span><span class="src"> use &quot;regression_coefficients.dta&quot;, clear</span></span><span class="code-line"><span class="ln" aria-hidden="true">81</span><span class="src"> quietly ds, has(type numeric)</span></span><span class="code-line"><span class="ln" aria-hidden="true">82</span><span class="src"> format `r(varlist)&#x27; %21.15g</span></span><span class="code-line"><span class="ln" aria-hidden="true">83</span><span class="src"> export delimited using &quot;regression_coefficients.csv&quot;, datafmt replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">84</span><span class="src">restore</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="07 · 手工整理系数、t 检验与置信区间:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L71–72 · <code>tempname</code>、<code>postfile</code></td><td>建立系数结果表。term 用 str12 保存不超过 12 字节的短字符串变量名;其余字段 estimate、se、t、p、ci_low、ci_high 用 double。本例变量名均为 ASCII。</td></tr><tr><td>L73 · <code>foreach term in income _cons</code></td><td>循环处理收入系数和截距,最终输出两行结果。</td></tr><tr><td>L74 · <code>tval = _b[...] / _se[...]</code></td><td>计算检验系数等于 0 的 t 值;分子没有减去其他假设值,因此原假设是该系数为 0。</td></tr><tr><td>L75 · <code>invttail(e(df_r), .025)</code></td><td>得到 t 分布右尾概率 0.025 的临界值,即双侧 95% 区间所用的 t₀.₉₇₅,₉₆;.025 不表示区间置信度为 2.5%。</td></tr><tr><td>L76 · <code>post</code></td><td>依次写入变量名、系数、标准误、t 值、双侧 p 值,以及置信区间上下限。abs(tval) 取绝对值,ttail 求右尾概率,再乘 2。</td></tr><tr><td>L77–78 · 循环结束、<code>postclose</code></td><td>完成两行写入,关闭系数表。</td></tr><tr><td>L79–84 · <code>preserve</code> 至 <code>restore</code></td><td>暂存家庭明细,读取系数表、设置数值格式并导出 CSV,再恢复家庭明细。模型与数据是两个层面的对象。</td></tr></tbody></table></div><div class="formula">t = β̂ / SE(β̂);p = 2 × P(T₉₆ ≥ |t|);95% CI = β̂ ± t₀.₉₇₅,₉₆ × SE(β̂)。</div><div class="table-wrap" tabindex="0" role="region" aria-label="07 · 手工整理系数、t 检验与置信区间:解释表"><table><thead><tr><th scope="col">变量</th><th scope="col">估计系数</th><th scope="col">常规标准误</th><th scope="col">t</th><th scope="col">p</th><th scope="col">95% 置信区间</th></tr></thead><tbody><tr><td>income</td><td>0.728799</td><td>0.020302</td><td>35.8970</td><td>1.95192e-57</td><td>[0.688499, 0.769099]</td></tr><tr><td>_cons</td><td>22.930934</td><td>47.096629</td><td>0.4869</td><td>0.627445</td><td>[-70.555136, 116.417004]</td></tr></tbody></table></div><p>临界值约为 1.984984。收入系数显著为正;截距的常规 p 值约 0.627,不能拒绝截距为 0。很小的 p 值不等于系数具有很大的经济效应。当前采用常规 OLS 标准误;有限样本精确 t/F 推断还需要相应模型条件,不能只看公式就认定条件成立。[S2]、[S7]、[S9]</p></section><section id="residual" aria-labelledby="heading-residual"><div class="section-heading"><h2 id="heading-residual">08 · 核对 OLS 残差的两个代数性质</h2><span class="line-badge">L86–97</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L86–97</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">86</span><span class="src">quietly summarize residual, meanonly</span></span><span class="code-line"><span class="ln" aria-hidden="true">87</span><span class="src">scalar residual_sum = r(sum)</span></span><span class="code-line"><span class="ln" aria-hidden="true">88</span><span class="src">generate double income_residual = income * residual</span></span><span class="code-line"><span class="ln" aria-hidden="true">89</span><span class="src">quietly summarize income_residual, meanonly</span></span><span class="code-line"><span class="ln" aria-hidden="true">90</span><span class="src">scalar income_residual_sum = r(sum)</span></span><span class="code-line"><span class="ln" aria-hidden="true">91</span><span class="src">display &quot;Sum of residuals = &quot; %21.12g scalar(residual_sum)</span></span><span class="code-line"><span class="ln" aria-hidden="true">92</span><span class="src">display &quot;Sum of income * residual = &quot; %21.12g scalar(income_residual_sum)</span></span><span class="code-line"><span class="ln" aria-hidden="true">93</span><span class="src">drop income_residual</span></span><span class="code-line"><span class="ln" aria-hidden="true">94</span><span class="src">save &quot;households_fitted.dta&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">95</span><span class="src">quietly ds, has(type numeric)</span></span><span class="code-line"><span class="ln" aria-hidden="true">96</span><span class="src"> format `r(varlist)&#x27; %21.15g</span></span><span class="code-line"><span class="ln" aria-hidden="true">97</span><span class="src">export delimited using &quot;households_fitted.csv&quot;, datafmt replace</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="08 · 核对 OLS 残差的两个代数性质:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L86–87 · <code>summarize residual, meanonly</code></td><td>meanonly 省去方差计算并抑制汇总显示,但仍返回 r(sum);把残差和存入标量 residual_sum。</td></tr><tr><td>L88–90 · 生成并汇总 <code>income_residual</code></td><td>计算每条观测的 income × residual,再把乘积之和保存到 income_residual_sum。</td></tr><tr><td>L91–92 · <code>display ... scalar(...)</code></td><td>按 %21.12g 打印两个标量。这里的 % 格式控制显示,不改变原数值。</td></tr><tr><td>L93 · <code>drop income_residual</code></td><td>删除仅用于核对的乘积变量,保留其汇总标量。</td></tr><tr><td>L94–97 · 保存 / 导出</td><td>把含 fitted、residual、residual_sq 的 98 条明细写入 households_fitted.dta 和 CSV。</td></tr></tbody></table></div><div class="formula">含截距 OLS 的正规方程:Σêᵢ = 0,ΣXᵢêᵢ = 0(数值计算允许微小舍入误差)。</div><p>现有输出:Σêᵢ = -1.955414e-11,ΣXᵢêᵢ = -7.333438e-08,都在浮点精度下接近 0。以 C4 为例,income=800、consume=561,拟合消费约 605.969927,残差约 -44.969927 元,表示实际消费低于拟合值。</p><aside class="note"><strong>不是模型假设检验</strong><p>这两个零和性质由当前含截距 OLS 的求解方式保证,不能证明总体 E(u|X)=0,不能证明不存在遗漏变量,也不能证明同方差。它们适合检查计算过程是否一致。</p></aside><p>本段 meanonly 的行为依据 [S5];残差定义及 OLS 结果依据 [S7]。上面两个等式可直接由残差平方和对截距和斜率求导得到。</p></section><section id="group" aria-labelledby="heading-group"><div class="section-heading"><h2 id="heading-group">09 · 按收入水平生成汇总表</h2><span class="line-badge">L99–109</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L99–109</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">99</span><span class="src">preserve</span></span><span class="code-line"><span class="ln" aria-hidden="true">100</span><span class="src"> collapse (count) n=consume (mean) mean_consume=consume (sd) sd_consume=consume (min) min_consume=consume (max) max_consume=consume, by(income)</span></span><span class="code-line"><span class="ln" aria-hidden="true">101</span><span class="src"> recast double mean_consume sd_consume</span></span><span class="code-line"><span class="ln" aria-hidden="true">102</span><span class="src"> generate double fitted_mean = scalar(intercept_ols) + scalar(slope_ols)*income</span></span><span class="code-line"><span class="ln" aria-hidden="true">103</span><span class="src"> generate double mean_residual = mean_consume - fitted_mean</span></span><span class="code-line"><span class="ln" aria-hidden="true">104</span><span class="src"> save &quot;income_group_summary.dta&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">105</span><span class="src"> quietly ds, has(type numeric)</span></span><span class="code-line"><span class="ln" aria-hidden="true">106</span><span class="src"> format `r(varlist)&#x27; %21.15g</span></span><span class="code-line"><span class="ln" aria-hidden="true">107</span><span class="src"> export delimited using &quot;income_group_summary.csv&quot;, datafmt replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">108</span><span class="src"> list, noobs separator(0)</span></span><span class="code-line"><span class="ln" aria-hidden="true">109</span><span class="src">restore</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="09 · 按收入水平生成汇总表:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L99 · <code>preserve</code></td><td>保存逐户明细,以便汇总后恢复。</td></tr><tr><td>L100 · <code>collapse ... , by(income)</code></td><td>按收入分组,把 98 条明细替换成 10 条分组记录;(count) 数非缺失消费条数,(mean) 求均值,(sd) 求组内样本标准差,(min)/(max) 求范围。</td></tr><tr><td>L100 · <code>n=consume</code> 等写法</td><td>左侧是汇总后的新变量名,右侧是被汇总的原变量。例如 mean_consume=consume 生成消费均值。</td></tr><tr><td>L101 · <code>recast double ...</code></td><td>保证均值、标准差的后续存储类型为 double;类型扩展不能恢复此前若已发生的精度损失。</td></tr><tr><td>L102 · <code>fitted_mean</code></td><td>用此前保存的截距和斜率计算每个收入水平的拟合均值;没有重新对 10 个均值做回归。</td></tr><tr><td>L103 · <code>mean_residual</code></td><td>组内实际均值减去线性拟合值。同组收入相同,所以也等于该组逐户残差的平均值。</td></tr><tr><td>L104–108 · 保存、导出并 <code>list</code></td><td>将分组表保存为 DTA/CSV,并在日志中显示。</td></tr><tr><td>L109 · <code>restore</code></td><td>恢复 98 条逐户明细;后面的散点图因此基于家庭记录。</td></tr></tbody></table></div><div class="table-wrap" tabindex="0" role="region" aria-label="09 · 按收入水平生成汇总表:解释表"><table><thead><tr><th scope="col">收入</th><th scope="col">n</th><th scope="col">组内均值</th><th scope="col">组内标准差</th><th scope="col">拟合均值</th><th scope="col">平均残差</th></tr></thead><tbody><tr><td>800</td><td>4</td><td>605.000</td><td>34.785</td><td>605.970</td><td>-0.970</td></tr><tr><td>1100</td><td>6</td><td>825.000</td><td>121.698</td><td>824.610</td><td>+0.390</td></tr><tr><td>1400</td><td>11</td><td>1045.000</td><td>116.309</td><td>1043.249</td><td>+1.751</td></tr><tr><td>1700</td><td>13</td><td>1265.000</td><td>137.683</td><td>1261.889</td><td>+3.111</td></tr><tr><td>2000</td><td>13</td><td>1485.000</td><td>135.988</td><td>1480.528</td><td>+4.472</td></tr><tr><td>2300</td><td>13</td><td>1682.154</td><td>154.879</td><td>1699.168</td><td>-17.014</td></tr><tr><td>2600</td><td>13</td><td>1925.000</td><td>165.183</td><td>1917.808</td><td>+7.192</td></tr><tr><td>2900</td><td>10</td><td>2136.200</td><td>125.612</td><td>2136.447</td><td>-0.247</td></tr><tr><td>3200</td><td>9</td><td>2350.333</td><td>203.426</td><td>2355.087</td><td>-4.754</td></tr><tr><td>3500</td><td>6</td><td>2583.167</td><td>248.066</td><td>2573.727</td><td>+9.440</td></tr></tbody></table></div><p>OLS 不要求每个收入组的平均残差都等于 0;这里满足的是全样本正规方程。各组人数不同,不能用 10 个组均值的不加权回归替代当前的逐户回归。组内标准差也不是均值的标准误。collapse 命令依据 [S10]。</p></section><section id="plot" aria-labelledby="heading-plot"><div class="section-heading"><h2 id="heading-plot">10 · 绘制散点与拟合直线,导出四种图形</h2><span class="line-badge">L111–117</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L111–117</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">111</span><span class="src">set scheme s2color</span></span><span class="code-line"><span class="ln" aria-hidden="true">112</span><span class="src">graph set window fontface &quot;SimSun&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">113</span><span class="src">twoway (scatter consume income, mcolor(&quot;26 71 111&quot;) msymbol(O) msize(small)) (lfit consume income, lcolor(&quot;174 44 51&quot;) lwidth(medthin)), title(&quot;不同可支配收入水平组家庭消费支出的条件分布图&quot;, size(medium) color(navy)) xtitle(&quot;每月可支配收入(元)&quot;, size(medsmall)) ytitle(&quot;每月消费支出(元)&quot;, size(medsmall)) xlabel(1000(500)3500) ylabel(500(500)3000, angle(90) grid glcolor(&quot;225 236 238&quot;)) xscale(range(500 4000)) yscale(range(0 3600)) legend(order(1 &quot;consume&quot; 2 &quot;Fitted values&quot;) rows(1) region(lcolor(black) fcolor(white))) graphregion(color(&quot;234 242 243&quot;)) plotregion(color(white)) xsize(9) ysize(6.55) name(consumption_fit, replace)</span></span><span class="code-line"><span class="ln" aria-hidden="true">114</span><span class="src">graph save &quot;consumption_fit.gph&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">115</span><span class="src">graph export &quot;consumption_fit.png&quot;, width(1800) replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">116</span><span class="src">graph export &quot;consumption_fit.svg&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">117</span><span class="src">graph export &quot;consumption_fit.pdf&quot;, replace</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="10 · 绘制散点与拟合直线,导出四种图形:解释表"><table><thead><tr><th scope="col">行号 / 选项</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L111 · <code>set scheme s2color</code></td><td>使用 s2color 图形样式方案。</td></tr><tr><td>L112 · <code>graph set window fontface &quot;SimSun&quot;</code></td><td>把图形窗口字体设为宋体,以支持这里的中文标题与坐标轴文字;实际显示取决于本机字体。</td></tr><tr><td>L113 · <code>twoway (...) (...)</code></td><td>把两个图层叠加在同一坐标系:scatter 散点层与 lfit 线性拟合层。</td></tr><tr><td><code>scatter consume income</code></td><td>先写纵轴变量消费,后写横轴变量收入;每条家庭记录对应一个点,完全相同的点会重合。</td></tr><tr><td><code>mcolor(&quot;26 71 111&quot;) msymbol(O) msize(small)</code></td><td>散点为指定 RGB 深蓝色、圆形符号、小尺寸。</td></tr><tr><td><code>lfit consume income</code></td><td>使用当前数据拟合带截距的一元 OLS 直线并绘制,不是把相邻散点连起来,也不直接读取 fitted 列。当前数据和设定相同,因此与前面的 OLS 拟合线一致。</td></tr><tr><td><code>lcolor(&quot;174 44 51&quot;) lwidth(medthin)</code></td><td>拟合线为指定 RGB 红色、中偏细线宽。</td></tr><tr><td><code>title(...) xtitle(...) ytitle(...)</code></td><td>分别设置主标题、横轴标题、纵轴标题及文字大小;navy 指定标题颜色。</td></tr><tr><td><code>xlabel(1000(500)3500)</code></td><td>横轴刻度从 1000 到 3500,间隔 500;这是刻度控制,不是筛选收入。</td></tr><tr><td><code>ylabel(500(500)3000, angle(90) grid glcolor(...))</code></td><td>纵轴刻度从 500 到 3000、间隔 500;标签旋转 90 度,添加指定浅色网格。</td></tr><tr><td><code>xscale(range(500 4000)) yscale(range(0 3600))</code></td><td>设置坐标轴范围,留出边距;不删除范围之外的记录,也不改变回归样本。</td></tr><tr><td><code>legend(order(1 ... 2 ...) rows(1) region(...))</code></td><td>图例按散点、拟合线的顺序排列成一行,并设黑色边框、白色背景。</td></tr><tr><td><code>graphregion(...) plotregion(...)</code></td><td>整张图背景设为浅蓝色,内部绘图区设为白色。</td></tr><tr><td><code>xsize(9) ysize(6.55)</code></td><td>指定图形物理宽高(英寸),决定总体比例;PNG 像素宽度在导出时另设。</td></tr><tr><td><code>name(consumption_fit, replace)</code></td><td>给内存图形命名,并允许替换同名内存图;与磁盘文件覆盖是不同层次。</td></tr><tr><td>L114 · <code>graph save ...gph</code></td><td>保存 Stata 原生图形,可在 Stata 中重新打开。</td></tr><tr><td>L115 · <code>graph export ...png, width(1800)</code></td><td>导出宽 1800 像素的位图。</td></tr><tr><td>L116–117 · SVG、PDF 导出</td><td>导出可缩放矢量图与适合打印的 PDF;这些 replace 允许覆盖对应磁盘文件。</td></tr></tbody></table></div><figure><img src="data:image/png;base64,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" alt="现有 Stata 输出:家庭消费散点与 OLS 拟合线(2026-10-23)" width="1800" height="1310"><figcaption>现有 Stata 输出:家庭消费散点与 OLS 拟合线(2026-10-23)</figcaption></figure><p>这幅图没有置信带,也没有预测区间。固定收入处的竖直点列是该收入组的经验消费分布,不意味着已知真实总体分布。原文件 L113 是一整条长命令,本页面仅自动折行显示,没有改变原始语句。[S11]</p></section><section id="robust" aria-labelledby="heading-robust"><div class="section-heading"><h2 id="heading-robust">11 · 计算异方差稳健标准误并导出</h2><span class="line-badge">L119–136</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L119–136</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">119</span><span class="src">* Heteroskedasticity-robust standard errors as a sensitivity check.</span></span><span class="code-line"><span class="ln" aria-hidden="true">120</span><span class="src">regress consume income, vce(robust)</span></span><span class="code-line"><span class="ln" aria-hidden="true">121</span><span class="src">estimates store Robust</span></span><span class="code-line"><span class="ln" aria-hidden="true">122</span><span class="src">estimates save &quot;consumption_robust.ster&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">123</span><span class="src">tempname robustcoef</span></span><span class="code-line"><span class="ln" aria-hidden="true">124</span><span class="src">postfile `robustcoef&#x27; str12 term double estimate double se double t double p double ci_low double ci_high using &quot;robust_coefficients.dta&quot;, replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">125</span><span class="src">foreach term in income _cons {</span></span><span class="code-line"><span class="ln" aria-hidden="true">126</span><span class="src"> scalar tval = _b[`term&#x27;] / _se[`term&#x27;]</span></span><span class="code-line"><span class="ln" aria-hidden="true">127</span><span class="src"> scalar crit = invttail(e(df_r), .025)</span></span><span class="code-line"><span class="ln" aria-hidden="true">128</span><span class="src"> post `robustcoef&#x27; (&quot;`term&#x27;&quot;) (_b[`term&#x27;]) (_se[`term&#x27;]) (tval) (2*ttail(e(df_r), abs(tval))) (_b[`term&#x27;]-crit*_se[`term&#x27;]) (_b[`term&#x27;]+crit*_se[`term&#x27;])</span></span><span class="code-line"><span class="ln" aria-hidden="true">129</span><span class="src">}</span></span><span class="code-line"><span class="ln" aria-hidden="true">130</span><span class="src">postclose `robustcoef&#x27;</span></span><span class="code-line"><span class="ln" aria-hidden="true">131</span><span class="src">preserve</span></span><span class="code-line"><span class="ln" aria-hidden="true">132</span><span class="src"> use &quot;robust_coefficients.dta&quot;, clear</span></span><span class="code-line"><span class="ln" aria-hidden="true">133</span><span class="src"> quietly ds, has(type numeric)</span></span><span class="code-line"><span class="ln" aria-hidden="true">134</span><span class="src"> format `r(varlist)&#x27; %21.15g</span></span><span class="code-line"><span class="ln" aria-hidden="true">135</span><span class="src"> export delimited using &quot;robust_coefficients.csv&quot;, datafmt replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">136</span><span class="src">restore</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="11 · 计算异方差稳健标准误并导出:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L119 · <code>* ...</code></td><td>行首星号表示注释,说明下一段是稳健标准误的敏感性检查,不执行运算。</td></tr><tr><td>L120 · <code>regress ... , vce(robust)</code></td><td>同一模型仍以 OLS 求系数,用异方差稳健协方差估计计算标准误;本例是非聚类 HC1,带 N/(N−k)=98/96 修正。</td></tr><tr><td>L121–122 · <code>estimates store/save</code></td><td>分别在内存和磁盘保存稳健版本,名字为 Robust、文件为 consumption_robust.ster。</td></tr><tr><td>L123–130 · 生成稳健系数表</td><td>复用 L71–78 的流程,但此时 _se[] 来自稳健协方差矩阵;脚本仍用 e(df_r)=96 的 t 分布计算 p 值和区间。</td></tr><tr><td>L131–136 · 导出并恢复数据</td><td>将 robust_coefficients.dta 转成 CSV,最后恢复逐户明细。</td></tr></tbody></table></div><div class="formula">HC1 协方差 = [N/(N−k)] × (X′X)⁻¹ [Σ xᵢxᵢ′êᵢ²] (X′X)⁻¹;这里 k=2,X 含截距列。</div><div class="table-wrap" tabindex="0" role="region" aria-label="11 · 计算异方差稳健标准误并导出:解释表"><table><thead><tr><th scope="col">变量</th><th scope="col">系数(两次相同)</th><th scope="col">常规 SE</th><th scope="col">HC1 SE</th><th scope="col">稳健 p 值</th><th scope="col">稳健 95% 区间</th></tr></thead><tbody><tr><td>income</td><td>0.728799</td><td>0.020302</td><td>0.021428</td><td>2.38147e-55</td><td>[0.686265, 0.771332]</td></tr><tr><td>_cons</td><td>22.930934</td><td>47.096629</td><td>43.447563</td><td>0.598867</td><td>[-63.311797, 109.173665]</td></tr></tbody></table></div><aside class="note"><strong>稳健标准误不一定更大</strong><p>本例收入系数的标准误从约 0.020302 增到 0.021428,而截距的标准误从约 47.096629 降到 43.447563。稳健处理针对方差估计,不会消除异方差,也不会解决遗漏变量或内生性。</p></aside><p>这里不是抗异常值的稳健回归算法(例如 rreg),也没有使用聚类标准误。稳健 t 推断仍依赖相应独立性、外生性和大样本近似条件。HC1 修正及当前 regress 行为依据 Stata 15 自带官方帮助 [S7]。</p></section><section id="hettest" aria-labelledby="heading-hettest"><div class="section-heading"><h2 id="heading-hettest">12 · 恢复 OLS 并进行异方差检验</h2><span class="line-badge">L137–140</span></div><div class="code-block" data-source="ZXN0aW1hdGVzIHJlc3RvcmUgT0xTCmVzdGF0IGhldHRlc3QKc2NhbGFyIGJwX2NoaTIgPSByKGNoaTIpCnNjYWxhciBicF9wID0gcihwKQ=="><div class="code-toolbar"><span>STATA · 原文件 L137–140</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">137</span><span class="src">estimates restore OLS</span></span><span class="code-line"><span class="ln" aria-hidden="true">138</span><span class="src">estat hettest</span></span><span class="code-line"><span class="ln" aria-hidden="true">139</span><span class="src">scalar bp_chi2 = r(chi2)</span></span><span class="code-line"><span class="ln" aria-hidden="true">140</span><span class="src">scalar bp_p = r(p)</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="12 · 恢复 OLS 并进行异方差检验:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L137 · <code>estimates restore OLS</code></td><td>恢复 L56 保存的常规 OLS 估计结果。L136 的 restore 只恢复了数据,没有把当前稳健估计切回常规 OLS。</td></tr><tr><td>L138 · <code>estat hettest</code></td><td>执行 Breusch–Pagan / Cook–Weisberg 异方差检验。无变量列表时,默认以拟合值为方差解释变量;默认 normal 版本有独立正态扰动假定。</td></tr><tr><td>L139–140 · 保存 <code>r(chi2)</code> 和 <code>r(p)</code></td><td>把检验统计量及 p 值保存为标量,供最终模型汇总表使用。这里是 r() 而不是 e()。</td></tr></tbody></table></div><p>现有结果:χ²(1) = 8.700549,p = 0.003181142。在默认检验条件下,5% 水平拒绝同方差原假设,提示方差可能随拟合水平变化;不能据此断定是哪条记录有问题。</p><aside class="note"><strong>这一行 restore 有实际作用</strong><p>本机 Stata 15 的 hettest.ado 会拒绝直接接在 vce(robust) 的结果后运行。因此 estimates restore OLS 是必要的模型切换;即使两次系数相同,协方差类型也不同。</p></aside><p>不要把这里默认 normal 版本的统计量一概写成辅助回归的 N×R²;Stata 的 iid 选项才使用相应的 N×R² 版本。本文件没有添加 iid、fstat 或 rhs。命令行为已核对本机 regress_postestimation.sthlp 及 hettest.ado。[S7]</p></section><section id="model-export" aria-labelledby="heading-model-export"><div class="section-heading"><h2 id="heading-model-export">13 · 将模型汇总指标写成一行 CSV</h2><span class="line-badge">L142–161</span></div><div class="code-block" data-source="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"><div class="code-toolbar"><span>STATA · 原文件 L142–161</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">142</span><span class="src">preserve</span></span><span class="code-line"><span class="ln" aria-hidden="true">143</span><span class="src"> clear</span></span><span class="code-line"><span class="ln" aria-hidden="true">144</span><span class="src"> set obs 1</span></span><span class="code-line"><span class="ln" aria-hidden="true">145</span><span class="src"> generate N = scalar(N_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">146</span><span class="src"> generate intercept = scalar(intercept_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">147</span><span class="src"> generate slope = scalar(slope_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">148</span><span class="src"> generate r_squared = scalar(rsquared_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">149</span><span class="src"> generate root_mse = scalar(rmse_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">150</span><span class="src"> generate rss = scalar(rss_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">151</span><span class="src"> generate F = scalar(F_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">152</span><span class="src"> generate df_resid = scalar(df_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">153</span><span class="src"> generate p_F = scalar(pF_ols)</span></span><span class="code-line"><span class="ln" aria-hidden="true">154</span><span class="src"> generate residual_sum = scalar(residual_sum)</span></span><span class="code-line"><span class="ln" aria-hidden="true">155</span><span class="src"> generate income_residual_sum = scalar(income_residual_sum)</span></span><span class="code-line"><span class="ln" aria-hidden="true">156</span><span class="src"> generate bp_chi2 = scalar(bp_chi2)</span></span><span class="code-line"><span class="ln" aria-hidden="true">157</span><span class="src"> generate bp_p = scalar(bp_p)</span></span><span class="code-line"><span class="ln" aria-hidden="true">158</span><span class="src"> quietly ds, has(type numeric)</span></span><span class="code-line"><span class="ln" aria-hidden="true">159</span><span class="src"> format `r(varlist)&#x27; %21.15g</span></span><span class="code-line"><span class="ln" aria-hidden="true">160</span><span class="src"> export delimited using &quot;model_statistics.csv&quot;, datafmt replace</span></span><span class="code-line"><span class="ln" aria-hidden="true">161</span><span class="src">restore</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="13 · 将模型汇总指标写成一行 CSV:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L142–144 · <code>preserve</code>、<code>clear</code>、<code>set obs 1</code></td><td>先保存当前家庭数据,再清空数据并创建 1 条空观测。这里是 clear,不是开头的 clear all;前面保存的标量仍可使用。</td></tr><tr><td>L145–148 · <code>generate N/intercept/slope/r_squared</code></td><td>把样本量、截距、斜率、R² 标量复制为单行数据表的列。</td></tr><tr><td>L149–153 · <code>root_mse/rss/F/df_resid/p_F</code></td><td>复制误差尺度、残差平方和、常规 F、残差自由度及常规 F 检验 p 值。F 取自最初 OLS 标量,不是稳健回归的 F。</td></tr><tr><td>L154–157 · 残差和与 BP 结果</td><td>复制两项正规方程核对值及异方差检验统计量和 p 值。</td></tr><tr><td>L158–160 · 格式与导出</td><td>再次选择数值变量并设格式,将 13 列、1 行的结果导出为 model_statistics.csv。原代码没有为这个汇总表另存 DTA。</td></tr><tr><td>L161 · <code>restore</code></td><td>恢复原来的 98 条家庭明细。</td></tr></tbody></table></div><p>generate 没有逐一写 double,是因为 L4 已设置默认类型;例如 generate N = scalar(N_ols) 得到一个数值变量。这里 N 只是列名,区别于 Stata 系统量 _N。该段的用意是把分散的标量整理成通用软件易于读取的一行表。[S1]、[S3]、[S6]</p></section><section id="finish" aria-labelledby="heading-finish"><div class="section-heading"><h2 id="heading-finish">14 · 完成标记、关闭日志与退出</h2><span class="line-badge">L163–165</span></div><div class="code-block" data-source="ZGlzcGxheSAiV0VFSzdfQU5BTFlTSVNfQ09NUExFVEVEIgpsb2cgY2xvc2UKZXhpdCwgY2xlYXI="><div class="code-toolbar"><span>STATA · 原文件 L163–165</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true">163</span><span class="src">display &quot;WEEK7_ANALYSIS_COMPLETED&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true">164</span><span class="src">log close</span></span><span class="code-line"><span class="ln" aria-hidden="true">165</span><span class="src">exit, clear</span></span></code></pre></div><div class="table-wrap" tabindex="0" role="region" aria-label="14 · 完成标记、关闭日志与退出:解释表"><table><thead><tr><th scope="col">行号 / 命令</th><th scope="col">解释</th></tr></thead><tbody><tr><td>L163 · <code>display &quot;WEEK7_ANALYSIS_COMPLETED&quot;</code></td><td>打印完成标记,用于定位是否执行到末尾。检查日志时应查找实际输出的标记行,而不只搜索被回显的 display 命令。</td></tr><tr><td>L164 · <code>log close</code></td><td>关闭显式打开的分析日志,让日志完整写入磁盘。</td></tr><tr><td>L165 · <code>exit, clear</code></td><td>在 do 文件中结束当前执行并返回调用者;clear 允许在退出 Stata 的情境下放弃未保存的数据,不是保存命令。通过 /e 启动时,批处理入口会在 do 执行结束后退出应用;若要从 do 内明确强制关闭 Stata,使用 exit, STATA clear。</td></tr></tbody></table></div><p>既有 week7_stata.log 中有独立的完成标记输出行和关闭日志记录,没有 r(数字); 错误结束行。为核对退出语境,另在给定 Stata 可执行文件中运行了不读取原数据的最小测试:子 do 执行 exit, clear 后,父 do 的下一条 display 仍能执行;这个测试没有重跑原分析脚本。有关调用情境参见本机官方 [P] exit 与 [R] exit 帮助。[S12]</p></section><section id="files" aria-labelledby="heading-files"><div class="section-heading"><h2 id="heading-files">文件索引:每个输出保存了什么</h2></div><div class="table-wrap" tabindex="0" role="region" aria-label="文件索引:每个输出保存了什么:解释表"><table><thead><tr><th scope="col">文件</th><th scope="col">内容 / 规模</th><th scope="col">产生位置</th></tr></thead><tbody><tr><td><code>source_totals_audit.dta</code> / <code>.csv</code></td><td>10 个收入组的明细计数与合计差额</td><td>L15–34</td></tr><tr><td><code>households_clean.dta</code> / <code>.csv</code></td><td>98 条家庭记录,4 个基础变量</td><td>L49–52</td></tr><tr><td><code>consumption_ols.ster</code></td><td>常规 OLS 估计结果</td><td>L57</td></tr><tr><td><code>regression_coefficients.dta</code> / <code>.csv</code></td><td>收入与截距两行常规系数表</td><td>L72–84</td></tr><tr><td><code>households_fitted.dta</code> / <code>.csv</code></td><td>98 条记录;4 个基础变量 + fitted、residual、residual_sq</td><td>L94–97</td></tr><tr><td><code>income_group_summary.dta</code> / <code>.csv</code></td><td>10 组;收入、人数、均值、标准差、最小值、最大值、拟合均值、平均残差</td><td>L104–107</td></tr><tr><td><code>consumption_fit.gph</code> / <code>.png</code> / <code>.svg</code> / <code>.pdf</code></td><td>同一散点与拟合线图的四种格式</td><td>L114–117</td></tr><tr><td><code>consumption_robust.ster</code></td><td>稳健协方差版本的估计结果</td><td>L122</td></tr><tr><td><code>robust_coefficients.dta</code> / <code>.csv</code></td><td>两行 HC1 系数推断表</td><td>L124–136</td></tr><tr><td><code>model_statistics.csv</code></td><td>1 行 13 列的模型汇总,未另存 DTA</td><td>L160</td></tr><tr><td><code>week7_stata.log</code></td><td>脚本主动打开的纯文本日志</td><td>L8、L164</td></tr><tr><td><code>week7_analysis.log</code></td><td>既有 /e 批处理执行产生的外层日志,不由脚本 log using 命名</td><td>运行方式产生</td></tr></tbody></table></div><p>本次新建的 Week7_Stata代码详解.md 和 Week7_Stata代码详解.html 是代码解释文档;原 do 文件不会自动生成它们。原有“Week7_回归分析报告”是结果报告,与本次逐段代码说明分别保留。</p></section><section id="checkpoints" aria-labelledby="heading-checkpoints"><div class="section-heading"><h2 id="heading-checkpoints">理解与复现时最容易出错的地方</h2></div><div class="table-wrap" tabindex="0" role="region" aria-label="理解与复现时最容易出错的地方:解释表"><table><thead><tr><th scope="col">容易误读的地方</th><th scope="col">正确读法</th></tr></thead><tbody><tr><td>把第 17 行合计当作额外家庭</td><td>合计只做审计;keep in 2/14 后它已被移除。</td></tr><tr><td>认为检出合计差额就已更正数据</td><td>程序只记录差异,回归始终使用可见明细。</td></tr><tr><td>认为所有 assert 都是统计假设检验</td><td>这里的 assert 是代码条件检查,失败时终止;它们没有检验显著性水平。</td></tr><tr><td>将空白当 0 或自动删掉重复金额</td><td>只删除 missing(consume);0 值和相同金额并不会因此被删掉。</td></tr><tr><td>把 excel_row 直接理解成家庭编号</td><td>它追踪原表行,长表中会跨收入重复;household_id 也是新建顺序号。</td></tr><tr><td>以为 format 可提高存储精度</td><td>double/recast 管存储,format 管显示,datafmt 决定 CSV 是否沿用该显示格式。</td></tr><tr><td>在系数导出循环中插入另一次 regress</td><td>会替换 e()、_b[]、_se[],使表格混入另一个模型结果。</td></tr><tr><td>将残差零和当作外生性证据</td><td>零和是含截距 OLS 的代数性质,不检验 E(u|X)=0。</td></tr><tr><td>将图中的线当作各组均值连线</td><td>lfit 是全样本一元 OLS 直线,组均值不必在线上。</td></tr><tr><td>以为 vce(robust) 消除了异方差</td><td>它调整推断所用协方差;当前系数、拟合值、残差不变。</td></tr><tr><td>把默认 hettest 当作无任何分布假定的检验</td><td>这里默认 normal 版本有相应假定,脚本没有请求 iid 版本。</td></tr><tr><td>把高 R² 解读成收入的因果作用</td><td>这是本组明细的单变量线性拟合,需要额外识别假设才能作因果解释。</td></tr></tbody></table></div></section><section id="run" aria-labelledby="heading-run"><div class="section-heading"><h2 id="heading-run">如何在给定路径下运行和查阅</h2></div><p>完整复现时,在 Stata 命令窗口运行下面的 do 命令。现有脚本包含 clear all、多处 replace 和末尾 exit;它面向完整批处理流程,重跑会覆盖同名分析输出。本文只说明原代码的这些实际行为。</p><div class="code-block" data-source="ZG8gIkM6L1VzZXJzL2NhdHRvbS9Eb2N1bWVudHMvZWNvbm9tZXRyaWNzL1dlZWs3L3dlZWs3X2FuYWx5c2lzLmRvIg=="><div class="code-toolbar"><span>STATA · 操作示例</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src">do &quot;C:/Users/cattom/Documents/econometrics/Week7/week7_analysis.do&quot;</span></span></code></pre></div><p>也可在 Windows PowerShell 启动独立 Stata 进程并等待完成。下面的可执行文件路径以 .exe 结束,不带末尾目录分隔符。此命令是供复现的示例,本次未执行。</p><div class="code-block" data-source="U3RhcnQtUHJvY2VzcyAtRmlsZVBhdGggIkQ6XFN0YXRhMTVcU3RhdGFTRS02NC5leGUiIGAKICAtQXJndW1lbnRMaXN0ICcvZSBkbyAiQzpcVXNlcnNcY2F0dG9tXERvY3VtZW50c1xlY29ub21ldHJpY3NcV2Vlazdcd2VlazdfYW5hbHlzaXMuZG8iJyBgCiAgLVdvcmtpbmdEaXJlY3RvcnkgIkM6XFVzZXJzXGNhdHRvbVxEb2N1bWVudHNcZWNvbm9tZXRyaWNzXFdlZWs3IiBgCiAgLVdpbmRvd1N0eWxlIEhpZGRlbiAtV2FpdA=="><div class="code-toolbar"><span>POWERSHELL · 操作示例</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src">Start-Process -FilePath &quot;D:\Stata15\StataSE-64.exe&quot; `</span></span><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src"> -ArgumentList &#x27;/e do &quot;C:\Users\cattom\Documents\econometrics\Week7\week7_analysis.do&quot;&#x27; `</span></span><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src"> -WorkingDirectory &quot;C:\Users\cattom\Documents\econometrics\Week7&quot; `</span></span><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src"> -WindowStyle Hidden -Wait</span></span></code></pre></div><p>读已有结果时,CSV 可以直接打开;DTA 用 use 读取,STER 用 estimates use 读取。例如:</p><div class="code-block" data-source="dXNlICJDOi9Vc2Vycy9jYXR0b20vRG9jdW1lbnRzL2Vjb25vbWV0cmljcy9XZWVrNy9ob3VzZWhvbGRzX2ZpdHRlZC5kdGEiLCBjbGVhcgplc3RpbWF0ZXMgdXNlICJDOi9Vc2Vycy9jYXR0b20vRG9jdW1lbnRzL2Vjb25vbWV0cmljcy9XZWVrNy9jb25zdW1wdGlvbl9vbHMuc3RlciIKZXN0aW1hdGVzIHJlcGxheQ=="><div class="code-toolbar"><span>STATA · 操作示例</span><button type="button" class="copy-btn">复制代码</button></div><pre><code><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src">use &quot;C:/Users/cattom/Documents/econometrics/Week7/households_fitted.dta&quot;, clear</span></span><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src">estimates use &quot;C:/Users/cattom/Documents/econometrics/Week7/consumption_ols.ster&quot;</span></span><span class="code-line"><span class="ln" aria-hidden="true"></span><span class="src">estimates replay</span></span></code></pre></div><p>若要交互式逐段学习,可在另存的练习副本中分段运行,并把宏定义、循环以及对应的 preserve/restore 放在同一执行块内。不要直接把带 L 行号的展示文本当作可执行命令;网页代码块的“复制代码”按钮复制的是无行号的原代码。</p></section><section id="sources" aria-labelledby="heading-sources"><div class="section-heading"><h2 id="heading-sources">核对依据与文档范围</h2></div><p>以下来源均是本机可直接核查的文件,命令说明优先对应 Stata 15 安装附带的官方帮助。本文不依赖在线脚本、字体或公式服务。网页图形内嵌,可离线单独阅读;Markdown 使用同目录 consumption_fit.png 的相对图片引用。</p><div class="table-wrap" tabindex="0" role="region" aria-label="核对依据与文档范围:解释表"><table><thead><tr><th scope="col">编号</th><th scope="col">本机官方文档(相对 D:/Stata15/ado/base/)</th><th scope="col">支撑内容</th></tr></thead><tbody><tr><td>[S1]</td><td><code>v/version.sthlp</code>、<code>c/clear.sthlp</code>、<code>g/generate.sthlp</code>、<code>m/macro.sthlp</code></td><td>版本控制、清空数据、新变量类型、局部宏等。</td></tr><tr><td>[S2]</td><td><code>p/post.sthlp</code></td><td>postfile/post/postclose、文件句柄、逐行写入表。</td></tr><tr><td>[S3]</td><td><code>f/format.sthlp</code>、<code>i/import_delimited.sthlp</code></td><td>显示格式、datafmt 与 CSV 导出。</td></tr><tr><td>[S4]</td><td><code>i/import_excel.sthlp</code>、<code>r/reshape.sthlp</code></td><td>Excel 导入与宽长表转换。</td></tr><tr><td>[S5]</td><td><code>s/summarize.sthlp</code></td><td>summarize、meanonly、r(N)/r(sum) 等返回值。</td></tr><tr><td>[S6]</td><td><code>p/preserve.sthlp</code></td><td>保存并恢复当前数据集。</td></tr><tr><td>[S7]</td><td><code>r/regress.sthlp</code>、<code>r/regress_postestimation.sthlp</code>、<code>h/hettest.ado</code></td><td>OLS、HC1、predict、e()、BP/CW 默认设定及 robust 后的限制。</td></tr><tr><td>[S8]</td><td><code>e/estimates_store.sthlp</code>、<code>e/estimates_save.sthlp</code></td><td>内存与磁盘估计结果存储。</td></tr><tr><td>[S9]</td><td><code>f/f_ttail.ihlp</code>、<code>f/f_invttail.ihlp</code>、<code>f/f_ftail.ihlp</code></td><td>ttail、invttail、Ftail 的官方函数说明(由同名 .sthlp 引用)。</td></tr><tr><td>[S10]</td><td><code>c/collapse.sthlp</code></td><td>组内 count/mean/sd/min/max 汇总。</td></tr><tr><td>[S11]</td><td><code>t/twoway_lfit.sthlp</code>、<code>s/scatter.sthlp</code> 及相应 graph 帮助</td><td>散点、线性拟合层及图形选项。</td></tr><tr><td>[S12]</td><td><code>e/exit.sthlp</code>、<code>e/exit_program.sthlp</code></td><td>退出应用与退出程序/do 文件的语境。</td></tr></tbody></table></div><p>数值依据:原始 Excel、week7_stata.log、households_clean.csv、households_fitted.csv、source_totals_audit.csv、regression_coefficients.csv、robust_coefficients.csv、income_group_summary.csv、model_statistics.csv。来源单元格、计数、系数、两种标准误、p 值与区间、拟合值、残差、R²、Root MSE、F、分组统计及默认 BP/CW 检验均已独立核对。</p><p>代码来源 SHA-256:<code>6b47d5ef559a1a68d866d73af54001ac84fb8d599debd4074b7858d22c673ffd</code>。行号与本文解释对应 2026 年 10 月 26 日读取的这份 165 行脚本;以后增删代码会改变行号。</p></section></main></div><footer>编写与核对 2026-10-26 · 结果日志 2026-10-23 · 原 do 文件与既有分析产物保持原样</footer><button type="button" id="back-top" class="back-top" aria-label="返回页面顶部">↑ 返回顶部</button><div id="copy-status" class="live-status" role="status" aria-live="polite"></div><script>
const statusEl = document.getElementById('copy-status');
let statusTimer;
function tell(message){statusEl.textContent=message;clearTimeout(statusTimer);statusTimer=setTimeout(()=>{statusEl.textContent='';},2300)}
document.querySelectorAll('.copy-btn').forEach(button=>button.addEventListener('click',async()=>{
const encoded=button.closest('.code-block').dataset.source;
const text=new TextDecoder().decode(Uint8Array.from(atob(encoded),c=>c.charCodeAt(0)));
try{
if(navigator.clipboard && window.isSecureContext){await navigator.clipboard.writeText(text)}
else{const area=document.createElement('textarea');area.value=text;area.style.position='fixed';area.style.opacity='0';document.body.append(area);area.select();const ok=document.execCommand('copy');area.remove();button.focus();if(!ok)throw new Error('copy failed')}
tell('已复制代码,不含行号');
}catch(error){tell('浏览器未允许复制,请选中代码手动复制')}
}));
document.getElementById('print-btn').addEventListener('click',()=>window.print());
document.getElementById('back-top').addEventListener('click',()=>window.scrollTo({top:0,behavior:window.matchMedia('(prefers-reduced-motion: reduce)').matches?'auto':'smooth'}));
const sectionNodes=[...document.querySelectorAll('main section')];
const navNodes=[...document.querySelectorAll('.sidebar a')];
let scrollPending=false;
function updateReading(){
const span=document.documentElement.scrollHeight-innerHeight;
document.getElementById('reading-progress').style.width=(span>0?Math.min(100,Math.max(0,scrollY/span*100)):0)+'%';
let current=sectionNodes[0].id;
for(const section of sectionNodes){if(section.getBoundingClientRect().top<=120)current=section.id;else break}
navNodes.forEach(link=>{if(link.getAttribute('href')==='#'+current)link.setAttribute('aria-current','true');else link.removeAttribute('aria-current')});
scrollPending=false;
}
addEventListener('scroll',()=>{if(!scrollPending){scrollPending=true;requestAnimationFrame(updateReading)}},{passive:true});
addEventListener('resize',updateReading);
document.querySelectorAll('.mobile-nav a').forEach(link=>link.addEventListener('click',()=>{link.closest('details').open=false}));
updateReading();
</script></body></html>